Generation and display of interactive 3D real estate models
Systems and methods are disclosed for the generation and interactive display of three-dimensional (3D) models that accurately represent buildings and other large, complex objects possessing both internal and external features. More specifically, an exterior mesh can be generated that captures all the external features of the building. An interior mesh can also be generated that captures all the internal features of the building. The exterior mesh and the interior mesh may be layered and combined using geographical coordinates (e.g., global positioning system (GPS) data) in order to create a combined mesh that can be used to render a 3D model of the object. Any images taken of external or internal features may also be appended to the 3D model or even overlaid on the 3D model (like textures), based on the location and directional view associated with those images.
1. A computer-implemented method comprising:
as implemented by a model generation and display system comprising one or more hardware processors,
generating an exterior mesh based on an exterior of a building, wherein the exterior mesh is associated with exterior mesh positioning data;
generating an interior mesh based on an interior of the building, wherein the interior mesh is associated with interior mesh positioning data;
orienting the exterior mesh relative to the interior mesh by referencing the exterior mesh positioning data and the interior mesh positioning data;
generating a combined mesh from the oriented exterior mesh and the interior mesh;
rendering a three-dimensional (3D) model of the building from the combined mesh;
dividing the 3D model into a plurality of locations based in part on structural features identified by machine learning in the combined mesh of the 3D model;
generating first metadata that associates an image of the interior of the building with a first location of the plurality of locations within an interior of the 3D model, wherein the location within the 3D model corresponds with a geographic location identified in second metadata of the image;
determining, using machine learning, that the image depicts a first type of room in the building;
classifying the location within the 3D model as being the first type of room; and
causing a monitor array to display the 3D model, wherein user input received via a sensor embedded in a table separate from the monitor array that detects movement controls a view of the 3D model displayed by the monitor array.
2. The method of claim 1 , wherein the image includes one of a captured image of the exterior of the building or a captured image of the interior of the building.
3. The method of claim 2 , wherein a view of the 3D model is a top-down view overlaid with a captured second image of a roof of the building.
4. The method of claim 2 , wherein the view of the 3D model shows an interior structure of the building and one or more second images of the interior.
5. The method of claim 1 , further comprising:
generating display data for a view of the 3D model of the building; and
providing the display data for the view to a display setup, wherein the display setup includes the monitor array and the table.
6. The computer-implemented method of claim 1 , wherein generating the exterior mesh of the building further comprises:
directing an aerial vehicle to fly around the building;
obtaining dimension data for the exterior of the building using the aerial vehicle;
obtaining exterior mesh positioning data using the aerial vehicle; and
capturing second images of the exterior of the building using the aerial vehicle.
7. The computer-implemented method of claim 1 , wherein
generating the interior mesh of the building further comprises:
obtaining dimension data for the interior of the building through a mobile device;
obtaining interior mesh positioning data using the mobile device; and
capturing second images of the interior of the building using the mobile device.
8. The computer-implemented method of claim 7 , wherein the second images of the interior of the building are 360 degree images.
9. The computer-implemented method of claim 1 , wherein the exterior mesh positioning data comprises global positioning system (GPS) coordinates.
10. The method of claim 1 , wherein the interior mesh positioning data comprises global positioning system (GPS) coordinates.
11. The method of claim 1 , wherein the table depicts a second view of the 3D model, and wherein the view of the 3D model displayed by the monitor array is different from the second view of the 3D model.
12. The method of claim 11 , wherein the table depicts controls to alter the view of the 3D model displayed by the monitor array.
13. Non-transitory computer storage media storing instructions that when executed by a system of one or more computers, cause the one or more computers to perform operations comprising:
generating an exterior mesh based on an exterior of a building, wherein the exterior mesh is associated with exterior mesh positioning data;
generating an interior mesh based on an interior of the building, wherein the interior mesh is associated with interior mesh positioning data;
orienting the exterior mesh relative to the interior mesh by referencing the exterior mesh positioning data and the interior mesh positioning data;
generating a combined mesh from the oriented exterior mesh and the interior mesh;
rendering a three-dimensional (3D) model of the building from the combined mesh;
dividing the 3D model into a plurality of locations based in part on structural features identified by machine learning in the combined mesh of the 3D model;
generating first metadata that associates an image of the interior of the building with a first location of the plurality of locations within an interior of the 3D model, wherein the location within the 3D model corresponds with a geographic location identified in second metadata of the image;
determining, using machine learning, that the image depicts a first type of room in the building;
classifying the location within the 3D model as being the first type of room; and
causing a monitor array to display the 3D model, wherein user input received via a sensor embedded in a table separate from the monitor array that detects movement controls a view of the 3D model displayed by the monitor array.
14. The non-transitory computer storage media of claim 13 , wherein the instructions further cause the one or more computers to perform operations comprising:
generating display data for a view of the 3D model of the building; and
providing the display data to for the view to a display setup, wherein the display setup includes the monitor array and the table.
15. The non-transitory computer storage media of claim 13 , wherein the instructions further cause the one or more computers to perform operations comprising:
directing an aerial vehicle to fly around the building;
obtaining dimension data for the exterior of the building using the aerial vehicle;
obtaining exterior mesh positioning data using the aerial vehicle; and
capturing second images of the exterior of the building using the aerial vehicle.
16. The non-transitory computer storage media of claim 13 , wherein the instructions further cause the one or more computers to perform operations comprising:
obtaining dimension data for the interior of the building through a mobile device;
obtaining interior mesh positioning data using the mobile device; and
capturing second images of the interior of the building using the mobile device.
17. The non-transitory computer storage media of claim 13 , wherein the image includes one of a captured image of the exterior of the building or a captured image of the interior of the building.
18. A model generation and display system comprising:
computer storage media storing instructions; and
one or more hardware processors configured to execute the instructions, wherein the instructions, when executed, cause the one or more hardware processors to perform operations comprising:
generating an exterior mesh based on an exterior of a building, wherein the exterior mesh is associated with exterior mesh positioning data;
generating an interior mesh based on an interior of the building, wherein the interior mesh is associated with interior mesh positioning data;
orienting the exterior mesh relative to the interior mesh by referencing the exterior mesh positioning data and the interior mesh positioning data;
generating a combined mesh from the oriented exterior mesh and the interior mesh;
rendering a three-dimensional (3D) model of the building from the combined mesh;
dividing the 3D model into a plurality of locations based in part on structural features identified by machine learning in the combined mesh of the 3D model;
generating first metadata that associates an image of the interior of the building with a first location of the plurality of locations within an interior of the 3D model, wherein the location within the 3D model corresponds with a geographic location identified in second metadata of the image;
determining, using machine learning, that the image depicts a first type of room in the building;
classifying the location within the 3D model as being the first type of room; and
causing a monitor array to display the 3D model, wherein user input received via a sensor embedded in a table separate from the monitor array that detects movement controls a view of the 3D model displayed by the monitor array.
19. The model generation and display system of claim 18 , wherein the instructions, when executed, cause the one or more hardware processors to further perform operations comprising:
generating display data for a view of the 3D model of the building; and
providing the display data for the view to a display setup, wherein the display setup includes the monitor array and the table.
20. The model generation and display system of claim 18 , wherein the instructions, when executed, cause the one or more hardware processors to further perform operations comprising:
directing an aerial vehicle to fly around the building;
obtaining dimension data for the exterior of the building using the aerial vehicle;
obtaining exterior mesh positioning data using the aerial vehicle; and
capturing second images of the exterior of the building using the aerial vehicle.
21. The model generation and display system of claim 20 , wherein the second images of the interior of the building are 360 degree images.
22. The model generation and display system of claim 18 , wherein the image includes one of a captured image of the exterior of the building or a captured image of the interior of the building.
23. The model generation and display system of claim 18 , wherein the table presents a second view different from the view of the 3D model displayed by the monitor array.